© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 502
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating connections or relationships between various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    connected with "and" or "&"

    np_acts-logits-general · gemini-2.0-flash

    connecting alternatives or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BASEPATH
    -0.59
     Kombat
    -0.59
    rzost
    -0.55
     OnInit
    -0.54
     verticale
    -0.54
    celotti
    -0.53
     snipers
    -0.52
    ffindor
    -0.51
     Testamento
    -0.51
     Aeronautics
    -0.51
    POSITIVE LOGITS
     Related
    0.70
     related
    0.67
    /*
    0.61
     ancillary
    0.60
    related
    0.59
    enumii
    0.58
     allied
    0.57
    Chham
    0.57
     дописавши
    0.57
    Related
    0.55
    Activations Density 0.438%

    No Known Activations